노이즈 레벨 및 유사도 평가 기반 저선량 조건의 전산화 단층 검사 영상에서의 비지역적 평균 알고리즘의 최적화
Optimization of Non-Local Means Algorithm in Low-Dose Computed Tomographic Image Based on Noise Level and Similarity Evaluations
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In this study, we optimized the FNLM algorithm through a simulation study and applied it to a phantom scanned by low-dose CT to evaluate whether the FNLM algorithm can be used to obtain improved image quality images. We optimized the FNLM algorithm with MASH phantom and FASH phantom, which the algorithm was applied with MATLAB, increasing the smoothing factor from 0.01 to 0.05 with increments of 0.001 and measuring COV, RMSE, and PSNR values of the phantoms. For both phantom, COV and RMSE decreased, and PSNR increased as the smoothing factor increased. Based on the above results, we optimized a smoothing factor value of 0.043 for the FNLM algorithm. Then we applied the optimized FNLM algorithm to low dose lung CT and lung CT under normal conditions. In both images, the COV de- creased by 55.33 times and 5.08 times respectively, and we confirmed that the quality of the image of low dose CT ap- plying the optimized FNLM algorithm was 5.08 times better than the image of lung CT under normal conditions. In conclusion, we found that the smoothing factor of 0.043 among the factors of the FNLM algorithm showed the best results and validated the performance by reducing the noise in the low-quality CT images due to low dose with the optimized FNLM algorithm.
Abstract
In this study, we optimized the FNLM algorithm through a simulation study and applied it to a phantom scanned by low-dose CT to evaluate whether the FNLM algorithm can be used to obtain improved image quality images. We optimized the FNLM algorithm with MASH phantom and FASH phantom, which the algorithm was applied with MATLAB, increasing the smoothing factor from 0.01 to 0.05 with increments of 0.001 and measuring COV, RMSE, and PSNR values of the phantoms. For both phantom, COV and RMSE decreased, and PSNR increased as the smoothing factor increased. Based on the above results, we optimized a smoothing factor value of 0.043 for the FNLM algorithm. Then we applied the optimized FNLM algorithm to low dose lung CT and lung CT under normal conditions. In both images, the COV de- creased by 55.33 times and 5.08 times respectively, and we confirmed that the quality of the image of low dose CT ap- plying the optimized FNLM algorithm was 5.08 times better than the image of lung CT under normal conditions. In conclusion, we found that the smoothing factor of 0.043 among the factors of the FNLM algorithm showed the best results and validated the performance by reducing the noise in the low-quality CT images due to low dose with the optimized FNLM algorithm.
참고문헌 (22)
- Singh D, "Classification of COVID-19 patients from chest CT images using multi-objective differential evolution-based convolutional neural networks", European Journal of Clinical Microbiology & Infectious Diseases, 39(7), pp.1379~1389 (2020)[DOI]
- Kim JS, "Clinical application and future of the latest CT", Journal of the Korean Magnet ics Society, 30(6), pp.233~238 (2020)[DOI]
- Ma J, "Low-dose computed tomography image restoration using previous normal-dose scan", Medical Physics, 38(10), pp.5713~5731 (2011)[DOI]
- Raman SP, "CT scan parameters and radiation dose : Practical advice for radiologists", Journal of the American College of Radiology, 10(11), pp.840~846 (2013)[DOI]
- Hamberg LM, "Multi-detector row CT : Radiation dose characteristics", Radiology, 226(3), pp.762~772 (2003)[DOI]
- Sarhan HG, "Recent advances in computed tomography radiation dosimetry", Asian Journal of Medical Technology, 3(1), pp.65~77 (2023)[DOI]
- Xiong T, "Improved adaptive kalman-median filter for line-scan x-ray transmission image", Sensors, 22(13) (2022)[DOI]
- Moghbela M, "Automatic liver segmentation on computed tomography using random walkers for treatment planning", EXCLI Journal, 15, pp.500~517 (2016)[DOI]
- Anam C, "An investigation of a CT noise reduction using a modified of wiener filtering-edge detection", Journal of Physics : Conference Series, 1217(1), pp.012022~ (2019)[DOI]
- Froment J, "Parameter-free fast pixelwise non-l ocal means denoising", Image Processing on Line, 4, pp.300~326 (2014)[DOI]
- Ghane B, "Quantitative analysis of image quality in low-dose computed tomography imaging for COVID-19 patients", Journal of Medical Signals & Sensors, 13(2), pp.118~128 (2023)[DOI]
- Buades A, "Non-local means denoising", Image Processing on Line, 1, pp.208~212 (2011)[DOI]
- Darbon J, "Fast nonlocal filtering applied to electron cryomic roscopy", 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp.1331~1334 (2008)
- Kim DH, "Empirical non-local algorithm for image and video denoising", 2013 IEEE International Conference on Consumer Electronics(ICCE), pp.498~499 (2013)
- Zimmer A, "CUDA optimization of non-local means extended to wrapped gaussian distributions for interferometric phase denoising", Procedia Computer Science, 80, pp.166~177 (2016)[DOI]
- Ahmed AS, "Medical denoising system based on stacked convolutional autoencoder for enhancing 2-dimensional gel electrophoresis noise reduction", Biomedical Signal Processing, 36, pp.102842~ (2021)[DOI]
- Oyama A, "Image quality improvement in cone-beam CT using the super-resolution technique", Journal of Radiation Research, 59(4), pp.501~510 (2018)[DOI]
- Kim BG, "Noise level and similarity analysis for computed tomographic thoracic image with fast non-local means denoising algorithm", Applied Sciences, 10(21) (2020)[DOI]
- Kang SH, "Application of fast non-local means algorithm for noise reduction using separable color channels in light microscopy images", International Journal of Environmental Research and Public Health, 18(6), pp.2903~ (2021)[DOI]
- Van De Ville D, "Non-local means with dimensionality reduction and SURE-Based parameter selection", IEEE Transactions on Image Processing, 20(9), pp.2683~2690 (2011)[DOI]
- Choi DH, "Image optimization of fast non local means noise reduction algorithm using various filtering factors with human anthropomorphic phantom : A simulation study", Journal of the Korean Society of Radiology, 13(3), pp.453~458 (2019)[DOI]
- Seo KH, "Optimization of smoothing factor for fast non-local means algorithm in high pitch based low-dose computed tomography images with tin-filter", Radiation Physics and Chemistry, 206, pp.110762~ (2023)[DOI]